bartowski/Qwen2.5-14B_Uncensored_Instruct-GGUF
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: bartowski/Qwen2.5-14B_Uncensored_Instruct-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-09 22:30:07 +08:00
commit 6ee4b945c4
28 changed files with 263 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

60
.gitattributes vendored Normal file
View File

@@ -0,0 +1,60 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncensored_Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncensored_Instruct-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncensored_Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncensored_Instruct-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncensored_Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncensored_Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncensored_Instruct-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncensored_Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncensored_Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncensored_Instruct-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncensored_Instruct-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncensored_Instruct-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncensored_Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncensored_Instruct-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncensored_Instruct-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncensored_Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncensored_Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncensored_Instruct-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncensored_Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncensored_Instruct-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncensored_Instruct-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncensored_Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncensored_Instruct-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncensored_Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-14B_Uncensored_Instruct.imatrix filter=lfs diff=lfs merge=lfs -text

3
Qwen2.5-14B_Uncensored_Instruct-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7cc28f0cb8a167e927740edfaff73e4f8b2ead5c2f3d0152d5b468c6fee2d9be
size 5356146432

3
Qwen2.5-14B_Uncensored_Instruct-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c1bbb43c304f9fc837bce7bbf4b73d185563fed3f24cb27b81d2e253550fdf0d
size 6916538112

3
Qwen2.5-14B_Uncensored_Instruct-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8b3bf09a2c352dc70754680bdc1229282e411dce6a4a55031950e1a54b514621
size 6383361792

3
Qwen2.5-14B_Uncensored_Instruct-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b922f7232316d8f248a12d91142f48be1431ba5b953a329dbc251bb60c9a4f10
size 8119840512

3
Qwen2.5-14B_Uncensored_Instruct-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f40375aa4882106c999603cea2d978fb12a2f1fe5e0780d50ce0ec4811aefa96
size 5770497792

3
Qwen2.5-14B_Uncensored_Instruct-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2bf19dcb9241fbdba615cb8c4e2271109808f561f0f3fc6787143f536a85f321
size 6530817792

3
Qwen2.5-14B_Uncensored_Instruct-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4d3e44d8159ea414b4c111b00075a865cf632e549c4fbb3856e2d24e975d1b8c
size 7924768512

3
Qwen2.5-14B_Uncensored_Instruct-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:78719834b341b4a4f25311863202ccdc19be604a2b478fb40037f8bab1ac9bd5
size 7339204352

3
Qwen2.5-14B_Uncensored_Instruct-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b34a7b0e4d63f71fd3d0e4a51382d988a3a81a525ed213b0e9a8f5382aeeb142
size 6659596032

3
Qwen2.5-14B_Uncensored_Instruct-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9fae6490c4442f3cdb509cc1a7b31308e33fe0e444bd327d00146210f363e6cc
size 8606015232

3
Qwen2.5-14B_Uncensored_Instruct-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b22706c52b9989b51dee3e6d005a94bba0608c64fad385749cc5eec0cdd83622
size 8544268032

3
Qwen2.5-14B_Uncensored_Instruct-Q4_0_4_4.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e641268f7b6e2b4a162eb5f18eb82e44ace8190a14113eb5704f6ce96d20413e
size 8517725952

3
Qwen2.5-14B_Uncensored_Instruct-Q4_0_4_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d4d63834d27bac29cbfa38088c42f564fbf5fc9e2108171017540986ac82291c
size 8517725952

3
Qwen2.5-14B_Uncensored_Instruct-Q4_0_8_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1db4d2d1953c2833530698b139adb4afce7e59b7a1a12917baf119a660e08cdb
size 8517725952

3
Qwen2.5-14B_Uncensored_Instruct-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6f52f53c0bd09a56f44a27270cd0277b05af8986a1383cfab00b0e2e1c3ec33e
size 9565953792

3
Qwen2.5-14B_Uncensored_Instruct-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f465c1956c3c43e82ff5df48a0d61e8d212de86f95e541b936237c5d8588f670
size 8988110592

3
Qwen2.5-14B_Uncensored_Instruct-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:78ac791a898c95173bb1f7daa0db1e064b9b035c132481bf003261fe5c7fe010
size 8573431552

3
Qwen2.5-14B_Uncensored_Instruct-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ba7c4649ab0211f00a5b2c0e08e08308c11a4978c928f2d8305cc750431acf4c
size 10989395712

3
Qwen2.5-14B_Uncensored_Instruct-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ed4dd029dc1d5f4a3185a36be17e042641a0d6f55965d5731c18e747b11abc33
size 10508873472

3
Qwen2.5-14B_Uncensored_Instruct-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3b3d796e8e7c064484d9bc1a85c180c618fb47cb18deda5e840dfc32a006ba08
size 10266554112

3
Qwen2.5-14B_Uncensored_Instruct-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:269b283f0f40b2774d261ae3c9c98d676a66a77762d908e6d0dde7ec1c2f64b1
size 12124684032

3
Qwen2.5-14B_Uncensored_Instruct-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c8efd8918d81ad3e282fe20ab36d03579b395cbb54bee66f8e911a07830368e4
size 12501802752

3
Qwen2.5-14B_Uncensored_Instruct-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:923339f0e9b98013c69804ca38710a3152bd6254d8cd8a68e6f9fdff3c334aa0
size 15701597952

3
Qwen2.5-14B_Uncensored_Instruct-f16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:43199294f0158adaf10e1b989160a1eb67c10e5a921b846f2da4ec2a2ab9ea1f
size 29547716064

3
Qwen2.5-14B_Uncensored_Instruct.imatrix Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:575c0ccaef7a6005bcf1e70a45ab361d87d3fbc5d17f8c4a9e4c298cd88b32b7
size 8563610

127
README.md Normal file
View File

@@ -0,0 +1,127 @@
---
base_model: SicariusSicariiStuff/Qwen2.5-14B_Uncensored_Instruct
language:
- en
license: apache-2.0
pipeline_tag: text-generation
quantized_by: bartowski
---
## Llamacpp imatrix Quantizations of Qwen2.5-14B_Uncensored_Instruct
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b3787">b3787</a> for quantization.
Original model: https://huggingface.co/SicariusSicariiStuff/Qwen2.5-14B_Uncensored_Instruct
All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)
Run them in [LM Studio](https://lmstudio.ai/)
## Prompt format
```
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Split | Description |
| -------- | ---------- | --------- | ----- | ----------- |
| [Qwen2.5-14B_Uncensored_Instruct-f16.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncensored_Instruct-GGUF/blob/main/Qwen2.5-14B_Uncensored_Instruct-f16.gguf) | f16 | 29.55GB | false | Full F16 weights. |
| [Qwen2.5-14B_Uncensored_Instruct-Q8_0.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncensored_Instruct-GGUF/blob/main/Qwen2.5-14B_Uncensored_Instruct-Q8_0.gguf) | Q8_0 | 15.70GB | false | Extremely high quality, generally unneeded but max available quant. |
| [Qwen2.5-14B_Uncensored_Instruct-Q6_K_L.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncensored_Instruct-GGUF/blob/main/Qwen2.5-14B_Uncensored_Instruct-Q6_K_L.gguf) | Q6_K_L | 12.50GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [Qwen2.5-14B_Uncensored_Instruct-Q6_K.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncensored_Instruct-GGUF/blob/main/Qwen2.5-14B_Uncensored_Instruct-Q6_K.gguf) | Q6_K | 12.12GB | false | Very high quality, near perfect, *recommended*. |
| [Qwen2.5-14B_Uncensored_Instruct-Q5_K_L.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncensored_Instruct-GGUF/blob/main/Qwen2.5-14B_Uncensored_Instruct-Q5_K_L.gguf) | Q5_K_L | 10.99GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [Qwen2.5-14B_Uncensored_Instruct-Q5_K_M.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncensored_Instruct-GGUF/blob/main/Qwen2.5-14B_Uncensored_Instruct-Q5_K_M.gguf) | Q5_K_M | 10.51GB | false | High quality, *recommended*. |
| [Qwen2.5-14B_Uncensored_Instruct-Q5_K_S.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncensored_Instruct-GGUF/blob/main/Qwen2.5-14B_Uncensored_Instruct-Q5_K_S.gguf) | Q5_K_S | 10.27GB | false | High quality, *recommended*. |
| [Qwen2.5-14B_Uncensored_Instruct-Q4_K_L.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncensored_Instruct-GGUF/blob/main/Qwen2.5-14B_Uncensored_Instruct-Q4_K_L.gguf) | Q4_K_L | 9.57GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [Qwen2.5-14B_Uncensored_Instruct-Q4_K_M.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncensored_Instruct-GGUF/blob/main/Qwen2.5-14B_Uncensored_Instruct-Q4_K_M.gguf) | Q4_K_M | 8.99GB | false | Good quality, default size for must use cases, *recommended*. |
| [Qwen2.5-14B_Uncensored_Instruct-Q3_K_XL.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncensored_Instruct-GGUF/blob/main/Qwen2.5-14B_Uncensored_Instruct-Q3_K_XL.gguf) | Q3_K_XL | 8.61GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [Qwen2.5-14B_Uncensored_Instruct-Q4_K_S.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncensored_Instruct-GGUF/blob/main/Qwen2.5-14B_Uncensored_Instruct-Q4_K_S.gguf) | Q4_K_S | 8.57GB | false | Slightly lower quality with more space savings, *recommended*. |
| [Qwen2.5-14B_Uncensored_Instruct-Q4_0.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncensored_Instruct-GGUF/blob/main/Qwen2.5-14B_Uncensored_Instruct-Q4_0.gguf) | Q4_0 | 8.54GB | false | Legacy format, generally not worth using over similarly sized formats |
| [Qwen2.5-14B_Uncensored_Instruct-Q4_0_8_8.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncensored_Instruct-GGUF/blob/main/Qwen2.5-14B_Uncensored_Instruct-Q4_0_8_8.gguf) | Q4_0_8_8 | 8.52GB | false | Optimized for ARM inference. Requires 'sve' support (see link below). |
| [Qwen2.5-14B_Uncensored_Instruct-Q4_0_4_8.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncensored_Instruct-GGUF/blob/main/Qwen2.5-14B_Uncensored_Instruct-Q4_0_4_8.gguf) | Q4_0_4_8 | 8.52GB | false | Optimized for ARM inference. Requires 'i8mm' support (see link below). |
| [Qwen2.5-14B_Uncensored_Instruct-Q4_0_4_4.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncensored_Instruct-GGUF/blob/main/Qwen2.5-14B_Uncensored_Instruct-Q4_0_4_4.gguf) | Q4_0_4_4 | 8.52GB | false | Optimized for ARM inference. Should work well on all ARM chips, pick this if you're unsure. |
| [Qwen2.5-14B_Uncensored_Instruct-IQ4_XS.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncensored_Instruct-GGUF/blob/main/Qwen2.5-14B_Uncensored_Instruct-IQ4_XS.gguf) | IQ4_XS | 8.12GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [Qwen2.5-14B_Uncensored_Instruct-Q3_K_L.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncensored_Instruct-GGUF/blob/main/Qwen2.5-14B_Uncensored_Instruct-Q3_K_L.gguf) | Q3_K_L | 7.92GB | false | Lower quality but usable, good for low RAM availability. |
| [Qwen2.5-14B_Uncensored_Instruct-Q3_K_M.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncensored_Instruct-GGUF/blob/main/Qwen2.5-14B_Uncensored_Instruct-Q3_K_M.gguf) | Q3_K_M | 7.34GB | false | Low quality. |
| [Qwen2.5-14B_Uncensored_Instruct-IQ3_M.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncensored_Instruct-GGUF/blob/main/Qwen2.5-14B_Uncensored_Instruct-IQ3_M.gguf) | IQ3_M | 6.92GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [Qwen2.5-14B_Uncensored_Instruct-Q3_K_S.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncensored_Instruct-GGUF/blob/main/Qwen2.5-14B_Uncensored_Instruct-Q3_K_S.gguf) | Q3_K_S | 6.66GB | false | Low quality, not recommended. |
| [Qwen2.5-14B_Uncensored_Instruct-Q2_K_L.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncensored_Instruct-GGUF/blob/main/Qwen2.5-14B_Uncensored_Instruct-Q2_K_L.gguf) | Q2_K_L | 6.53GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [Qwen2.5-14B_Uncensored_Instruct-IQ3_XS.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncensored_Instruct-GGUF/blob/main/Qwen2.5-14B_Uncensored_Instruct-IQ3_XS.gguf) | IQ3_XS | 6.38GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [Qwen2.5-14B_Uncensored_Instruct-Q2_K.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncensored_Instruct-GGUF/blob/main/Qwen2.5-14B_Uncensored_Instruct-Q2_K.gguf) | Q2_K | 5.77GB | false | Very low quality but surprisingly usable. |
| [Qwen2.5-14B_Uncensored_Instruct-IQ2_M.gguf](https://huggingface.co/bartowski/Qwen2.5-14B_Uncensored_Instruct-GGUF/blob/main/Qwen2.5-14B_Uncensored_Instruct-IQ2_M.gguf) | IQ2_M | 5.36GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
## Embed/output weights
Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.
Some say that this improves the quality, others don't notice any difference. If you use these models PLEASE COMMENT with your findings. I would like feedback that these are actually used and useful so I don't keep uploading quants no one is using.
Thanks!
## Downloading using huggingface-cli
First, make sure you have hugginface-cli installed:
```
pip install -U "huggingface_hub[cli]"
```
Then, you can target the specific file you want:
```
huggingface-cli download bartowski/Qwen2.5-14B_Uncensored_Instruct-GGUF --include "Qwen2.5-14B_Uncensored_Instruct-Q4_K_M.gguf" --local-dir ./
```
If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:
```
huggingface-cli download bartowski/Qwen2.5-14B_Uncensored_Instruct-GGUF --include "Qwen2.5-14B_Uncensored_Instruct-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (Qwen2.5-14B_Uncensored_Instruct-Q8_0) or download them all in place (./)
## Q4_0_X_X
These are *NOT* for Metal (Apple) offloading, only ARM chips.
If you're using an ARM chip, the Q4_0_X_X quants will have a substantial speedup. Check out Q4_0_4_4 speed comparisons [on the original pull request](https://github.com/ggerganov/llama.cpp/pull/5780#pullrequestreview-21657544660)
To check which one would work best for your ARM chip, you can check [AArch64 SoC features](https://gpages.juszkiewicz.com.pl/arm-socs-table/arm-socs.html) (thanks EloyOn!).
## Which file should I choose?
A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9)
The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.
If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.
If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.
Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.
If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.
If you want to get more into the weeds, you can check out this extremely useful feature chart:
[llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix)
But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.
These I-quants can also be used on CPU and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
The I-quants are *not* compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm.
## Credits
Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset
Thank you ZeroWw for the inspiration to experiment with embed/output
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski

1
configuration.json Normal file
View File

@@ -0,0 +1 @@
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}